Comments (4)
@ZhennanQin Please help addressing the issue.
from onednn.
diff --git a/src/graph/backend/graph_compiler/core/src/runtime/low_level_threadpool_wrapper.hpp b/src/graph/backend/graph_compiler/core/src/runtime/low_level_threadpool_wrapper.hpp
index 7c70a3ac0c..7881a927fa 100644
--- a/src/graph/backend/graph_compiler/core/src/runtime/low_level_threadpool_wrapper.hpp
+++ b/src/graph/backend/graph_compiler/core/src/runtime/low_level_threadpool_wrapper.hpp
@@ -17,7 +17,7 @@
#ifndef GRAPH_BACKEND_GRAPH_COMPILER_CORE_SRC_RUNTIME_LOW_LEVEL_THREADPOOL_WRAPPER_HPP
#define GRAPH_BACKEND_GRAPH_COMPILER_CORE_SRC_RUNTIME_LOW_LEVEL_THREADPOOL_WRAPPER_HPP
-#include <exception>
+#include <stdexcept>
#include "thread_locals.hpp"
#include <runtime/config.hpp>
#include <util/compiler_macros.hpp>
@@ -58,7 +58,7 @@ void call_threadpool(TSched *ths, main_func_t f, runtime::stream_t *stream,
ths = T::all_thread_prepare(ths, stream, threads);
if (threads > 1 || !T::can_optimize_single_thread) {
typename T::TyState rtl_state {T::before_parallel(ths)};
-
+ int64_t i = 0;
#if SC_CPU_THREADPOOL == SC_THREAD_POOL_OMP
SC_NO_OP();
#pragma omp parallel for
These changes help, but I did not test other runtime options.
from onednn.
Thanks for reporting this. https://github.com/intel-innersource/libraries.performance.math.onednn/pull/7755 is merged to fix this. Please let me know if you have further issues.
from onednn.
Thanks!
from onednn.
Related Issues (20)
- Performance with matmul HOT 9
- DNNL_TEST_SET NIGHTLY produces duplicate benchdnn tests HOT 1
- AMD oneDNN Build Error HOT 2
- could not create a primitive descriptor for a reorder primitive HOT 11
- Speed drop when running oneDNN in a subthread HOT 11
- python call sycl C++ Error
- brgconv:sve_256 uses a lot of memory HOT 4
- brg:sve_256 fails benchdnn accuracy tests
- The testcase test_graph_unit_dnnl_layer_norm_usm_cpu fails HOT 7
- Pytorch bias quantisation on aarch64 - how best to proceed? HOT 3
- Fix compilation of oneDNN with C++20 on Windows HOT 4
- [ACL] non-constant depthwise convolution weights leads to performance degradation HOT 2
- Build with SYCL fails using intel/llvm compiler HOT 5
- OneDNN 2.7.3 Compilation Error in TensorFlow on RISC-V HOT 2
- submemory_desc() throws exception HOT 3
- oneDNN - Build failure HOT 13
- Is ONNX support oneDNN with windows 11? HOT 3
- NGEN_ASM support is incomplete HOT 5
- [ARM] Support FP16 post-ops fusion into ACL kernels HOT 2
- [ARM] Suport 32-bits CPUs within ACL integration HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from onednn.